From 6e4ed7b00afc4dbc557bdaef28fdc25b0acf1e2c Mon Sep 17 00:00:00 2001
From: "github-actions[bot]"
 <41898282+github-actions[bot]@users.noreply.github.com>
Date: Mon, 6 Jul 2026 12:19:49 +0000
Subject: [PATCH] skill(github-agentic-workflows): add threat-detection
 reference URL to security-and-operations

Add link to https://github.github.com/gh-aw/reference/threat-detection/ in
the Safe Outputs section of security-and-operations.md, consistent with the
existing pattern of linking to cost-management, outcomes, and open-telemetry
reference pages. The GH-AW home page confirms this dedicated reference page
exists. Bump version to 1.6.

Co-authored-by: Copilot <223556219+Copilot@users.noreply.github.com>
---
 skills/github-agentic-workflows/SKILL.md                        | 2 +-
 .../references/security-and-operations.md                       | 2 +-
 2 files changed, 2 insertions(+), 2 deletions(-)

diff --git a/skills/github-agentic-workflows/SKILL.md b/skills/github-agentic-workflows/SKILL.md
index 3446088..6c891e0 100644
--- a/skills/github-agentic-workflows/SKILL.md
+++ b/skills/github-agentic-workflows/SKILL.md
@@ -4,7 +4,7 @@ description: Authors, reviews, installs, and debugs GitHub Agentic Workflows in
 license: MIT
 metadata:
   author: webmaxru
-  version: "1.5"
+  version: "1.6"
 ---
 
 # GitHub Agentic Workflows
diff --git a/skills/github-agentic-workflows/references/security-and-operations.md b/skills/github-agentic-workflows/references/security-and-operations.md
index 5668225..de45183 100644
--- a/skills/github-agentic-workflows/references/security-and-operations.md
+++ b/skills/github-agentic-workflows/references/security-and-operations.md
@@ -35,7 +35,7 @@ Key points:
 
 1. The agent runs read-only and emits a structured artifact describing its intended actions.
 2. Before any output is applied, a dedicated threat detection job runs an AI-powered scan of the agent's proposed changes. It checks for prompt injection attacks, leaked credentials, and malicious code patterns. If anything looks suspicious, the workflow fails immediately and nothing is written to the repository.
-3. After the threat detection gate, a separate job with scoped write permissions applies only what the workflow explicitly permits: hard limits per operation (such as a maximum of one issue per run), required title prefixes, and label constraints. The agent requests; a gated job decides.
+3. After the threat detection gate, a separate job with scoped write permissions applies only what the workflow explicitly permits: hard limits per operation (such as a maximum of one issue per run), required title prefixes, and label constraints. The agent requests; a gated job decides. See [https://github.github.com/gh-aw/reference/threat-detection/](https://github.github.com/gh-aw/reference/threat-detection/) for the full threat-detection reference.
 4. Common outputs include `create-issue`, `add-comment`, `add-labels`, `create-pull-request`, `dispatch-workflow`, `call-workflow`, `assign-to-agent`, and `create-agent-session`.
 5. `noop`, `missing-tool`, and `missing-data` are critical truthfulness and reliability tools.
 6. `staged: true` is the safest rollout mode for new write-heavy workflows.